INDEX

Explanations

symbols and structural elements related to user interface navigation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cala

-0.15

acher

-0.15

oader

-0.15

 Glob

-0.14

@Web

-0.14

elage

-0.14

urette

-0.14

oppers

-0.14

cheon

-0.14

ã

-0.14

POSITIVE LOGITS

ibble

0.15

0.14

antity

0.14

.spi

0.14

hom

0.13

removeAttr

0.13

chter

0.13

chrift

0.13

à¸¹à¸¥

0.13

Activations Density 0.013%

symbols and structural elements related to user interface navigation

No Comments

No Known Activations